Saved in:
Bibliographic Details
Main Authors: Coda-Forno, Julian, Zhao, Zhuokai, Zhang, Qiang, Tamboli, Dipesh, Li, Weiwei, Fan, Xiangjun, Zhang, Lizhu, Schulz, Eric, Tseng, Hsiao-Ping
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.00494
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Should LLM reasoning live in a separate module, or within a single model's forward pass and representational space? We study dual-architecture latent reasoning, where a fluent Base exchanges latent messages with a Coprocessor, and test two hypotheses aimed at improving latent communication over Liu et al. (2024): (H1) increase channel capacity; (H2) learn communication via joint finetuning. Under matched latent-token budgets on GPT-2 and Qwen-3, H2 is consistently strongest while H1 yields modest gains. A unified soft-embedding baseline, a single model with the same forward pass and shared representations, using the same latent-token budget, nearly matches H2 and surpasses H1, suggesting current dual designs mostly add compute rather than qualitatively improving reasoning. Across GSM8K, ProsQA, and a Countdown stress test with increasing branching factor, scaling the latent-token budget beyond small values fails to improve robustness. Latent analyses show overlapping subspaces with limited specialization, consistent with weak reasoning gains. We conclude dual-model latent reasoning remains promising in principle, but likely requires objectives and training schedules that explicitly shape latent spaces for algorithmic planning.